System Detail

iic/ eres2netv2-zh

eresv2_zh

ranked review: approved IIC ERes2NetV2

This page shows the global rank, scenario ranks, and trial-set results for this submission.

Back To Leaderboard Submit Another Run

Global Position

#6/18

Public ranking position among reviewed full-core submissions.

Scenario-Macro EER

11.5449

Scenario-Macro minDCF

0.484961

Coverage

26/26

1 scenario ranked #1 4 scenarios in top 3

Public Listing

Ranked Publicly

This full-core result is approved and included in the public ranking.

Model Provenance

Source and architecture

Displayed name: iic/eres2netv2-zh
Source: IIC
Architecture: ERes2NetV2
Submitted alias: speech_eres2netv2_sv_zh-cn_16k-common
Created at: 2026-05-29T14:35:20.759435+00:00

Training And Links

Training data and references

Training data: Large Chinese speaker corpus, about 200k speakers
Training setup: Official 16 kHz Chinese ERes2NetV2 release.
Submission mode: full-core
Paper: ERes2NetV2: Boosting Short-Duration Speaker Verification Performance with Computational Efficiency

Open Source Checkpoint Open Paper

Higher-Ranked Scenarios

Scenario ranks above the global position

Genre shift #1 Channel/device #2 Short-duration #2

Show 3 supporting trial sets

CN-Celeb: #1 on its trial-set ranking.
GSC Short: #1 on its trial-set ranking.
CN-Celeb Genre: #1 on its trial-set ranking.

Lower-Ranked Scenarios

Scenario ranks below the global position

Noise/reverb #13 Overlap #12 Aging #12

Show 3 supporting trial sets

VoxCeleb Short: #15 on its trial-set ranking.
VoxCeleb1-H: #14 on its trial-set ranking.
VoxCeleb1-O: #14 on its trial-set ranking.

Scenario Rankings

Full ranking across scenarios

This table shows where the model sits on each scenario, using source-balanced scenario scores and the linked trial sets as evidence.

Scenario	Rank	Lens	Evidence	Score
Genre-Shift Robustness Whether performance holds when CN-Celeb enrollment and test speech come from different source genres.	#1/18 Leader	Source-genre variation 0.0000 EER from leader	#1 14.2725	14.2725 0.527525 minDCF
Channel / Device Robustness How resilient the model is to device and channel mismatch.	#2/18 Top 3	Device and channel variation 5.6656 EER from leader	#4 17.4433 #2 6.5083	11.9758 0.644862 minDCF
Short-Duration Robustness How much performance holds up when speech evidence is limited by duration.	#2/18 Top 3	Short-duration speech 0.4551 EER from leader	#2 3.7090 #1 5.0750 #2 17.6675 #15 25.4264	12.9695 0.460887 minDCF
In-The-Wild Robustness How strong the model is on unconstrained celebrity and media speech across official CN-Celeb and VoxCeleb protocols.	#3/18 Top 3	Open-domain media speech 0.3535 EER from leader	#1 3.8243 #14 6.3852 #14 6.3659 #14 8.9975	5.5369 0.294964 minDCF
Distance Robustness How much performance changes across meeting and domestic distance mismatch.	#5/18 Competitive	Distance mismatch 2.0099 EER from leader	#2 14.1380 #2 5.8680 #13 18.3901 #2 6.6987	11.2737 0.537866 minDCF
Cross-Lingual Robustness How well speaker identity survives enrollment-test language mismatch.	#6/18 Competitive	Language mismatch 0.8643 EER from leader	#6 5.3320	5.3320 0.299692 minDCF
Speaking-Style Robustness Whether the model can preserve identity across emotion-driven change, whispered speech, and noise-induced Lombard speaking style.	#8/18 Competitive	Speaking style shift 3.1793 EER from leader	#12 7.5779 #2 9.1250 #12 1.2034	5.9688 0.361679 minDCF
Accent / Dialect Robustness How reliably the model tracks identity across accent and dialect mismatch.	#10/18 Needs work	Accent and dialect variation 3.3832 EER from leader	#13 26.7067 #9 20.9300	23.8183 0.764092 minDCF
Aging Robustness How stable identity representations remain across age-derived and longitudinal recording gaps.	#12/18 Needs work	Speaker aging and time gaps 7.2168 EER from leader	#12 11.4067 #12 7.1662	9.2864 0.497259 minDCF
Overlap Robustness How well speaker identity survives light, mid, and heavy overlap in both meeting and domestic recordings.	#12/18 Needs work	Overlapping speakers 4.7417 EER from leader	#2 6.5933 #12 23.1667	14.8800 0.543251 minDCF
Noise / Reverb Robustness How reliably the model preserves identity when room acoustics, distractor noise, and microphone placement deviate from an easier in-corpus reference condition.	#13/18 Needs work	Noise and reverberation 9.1000 EER from leader	#13 11.6800	11.6800 0.402500 minDCF

Trial-Set Results

Raw ranking by trial set

Expand this section to inspect the detailed trial-set rankings.

Show

Trial Set	Rank	Scenarios	Trials	Score
TidyVoiceX2-ASV TidyVoiceX2-ASV	#6/18	Cross-lingual	200000	5.3320 0.299692 minDCF
HI-MIA HI-MIA	#2/18	Short-duration	660000	3.7090 0.208377 minDCF
GSC Short Google Speech Commands	#1/18	Short-duration	220000	5.0750 0.303175 minDCF
GLOBE GLOBE	#13/18	Accent/dialect	56848	26.7067 0.580650 minDCF
CN-Celeb CN-Celeb	#1/18	In-the-wild	3484292	3.8243 0.165880 minDCF
CN-Celeb Genre CN-Celeb	#1/18	Genre shift	440000	14.2725 0.527525 minDCF
CN-Celeb Short CN-Celeb	#2/18	Short-duration	546964	17.6675 0.559834 minDCF
VoxCeleb1-O VoxCeleb1	#14/18	In-the-wild	37611	6.3852 0.421188 minDCF
VoxCeleb1-E VoxCeleb1	#14/18	In-the-wild	579818	6.3659 0.387641 minDCF
VoxCeleb1-H VoxCeleb1	#14/18	In-the-wild	550894	8.9975 0.463313 minDCF
VoxCeleb Short VoxCeleb1	#15/18	Short-duration	394724	25.4264 0.772160 minDCF
3D-Speaker Device 3D-Speaker	#4/18	Channel/device	180000	17.4433 0.869280 minDCF
3D-Speaker Distance 3D-Speaker	#2/18	Distance	175163	14.1380 0.723966 minDCF
3D-Speaker Dialect 3D-Speaker	#9/18	Accent/dialect	180000	20.9300 0.947533 minDCF
FFSVC 2022 Cross-Channel FFSVC 2022	#2/18	Channel/device	72000	6.5083 0.420444 minDCF
FFSVC 2022 Cross-Domain FFSVC 2022	#2/18	Distance	66546	6.6987 0.430696 minDCF
Whisper40 Whisper Whisper40	#2/18	Speaking style	17600	9.1250 0.663000 minDCF
Lombard Grid Lombard Lombard Grid	#12/18	Speaking style	29524	1.2034 0.075149 minDCF
VOiCES Noise/Reverb VOiCES	#13/18	Noise/reverb	55000	11.6800 0.402500 minDCF
CHiME-6 Domestic Far-Field CHiME-6	#13/18	Distance	36487	18.3901 0.771721 minDCF
CHiME-6 Overlap CHiME-6	#12/18	Overlap	39600	23.1667 0.743694 minDCF
ESD ESD	#12/18	Speaking style	437408	7.5779 0.346889 minDCF
AliMeeting Near/Far AliMeeting	#2/18	Distance	220000	5.8680 0.225080 minDCF
AliMeeting Overlap AliMeeting	#2/18	Overlap	165000	6.5933 0.342807 minDCF
VoxKnesset VoxKnesset	#12/18	Aging	158312	11.4067 0.527584 minDCF
VoxPopuli Aging VoxPopuli	#12/18	Aging	146575	7.1662 0.466934 minDCF